© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 13254
    Prev
    Next
    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hubbard
    -0.08
     каз
    -0.08
     Mus
    -0.08
     Krist
    -0.08
    asd
    -0.08
    itr
    -0.07
     nervous
    -0.07
     само
    -0.07
     Elliot
    -0.07
     Fors
    -0.07
    POSITIVE LOGITS
     marinade
    0.09
    �
    0.09
    渡
    0.08
    ૂત
    0.08
    0.08
    onium
    0.08
    (Code
    0.07
    Walls
    0.07
    ificates
    0.07
     parab
    0.07
    Activations Density 0.013%
    No Known Activations